Application of gray variation statistic in image retrieval
Xiaoying Tai · Computer Engineering and Applications Journal · 2007
Texture is a distinct character of an image,which is an important feature in many CBIR systems.In this paper a new method based on texture features is proposed,which statistic the gray-level variation between neighboring pixels at the directions of horizontal,vertical,45 degree and 135 degree.A prototype system is developed to compare this method with gray level co-occurrence matrix and texture spectrum in the retrieval accuracies,the rank and the execution time.Experiment results show that the proposed approach is effective.Meanwhile,a method combining both color and texture is proposed,and the technique of relevance feedback is used in the algorithm to enhance the effectiveness and accuracy by adjusting the feature parameters.